ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918520598560768 |
|---|---|
| author | Jin, Jiarui Wang, Haoyu Wu, Xingliang Fang, Xiaocheng Lan, Xiang Wang, Zihan Zhang, Deyun Liu, Bo Zhang, Yingying Wu, Xian Li, Hongyan Hong, Shenda |
| author_facet | Jin, Jiarui Wang, Haoyu Wu, Xingliang Fang, Xiaocheng Lan, Xiang Wang, Zihan Zhang, Deyun Liu, Bo Zhang, Yingying Wu, Xian Li, Hongyan Hong, Shenda |
| contents | Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning ECG MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code is available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04279 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation Jin, Jiarui Wang, Haoyu Wu, Xingliang Fang, Xiaocheng Lan, Xiang Wang, Zihan Zhang, Deyun Liu, Bo Zhang, Yingying Wu, Xian Li, Hongyan Hong, Shenda Computation and Language Electrocardiography (ECG) serves as an indispensable diagnostic tool in clinical practice, yet existing multimodal large language models (MLLMs) remain unreliable for ECG interpretation, often producing plausible but clinically incorrect analyses. To address this, we propose ECG-R1, the first reasoning ECG MLLM designed for reliable ECG interpretation via three innovations. First, we construct the interpretation corpus using \textit{Protocol-Guided Instruction Data Generation}, grounding interpretation in measurable ECG features and monograph-defined quantitative thresholds and diagnostic logic. Second, we present a modality-decoupled architecture with \textit{Interleaved Modality Dropout} to improve robustness and cross-modal consistency when either the ECG signal or ECG image is missing. Third, we present \textit{Reinforcement Learning with ECG Diagnostic Evidence Rewards} to strengthen evidence-grounded ECG interpretation. Additionally, we systematically evaluate the ECG interpretation capabilities of proprietary, open-source, and medical MLLMs, and provide the first quantitative evidence that severe hallucinations are widespread, suggesting that the public should not directly trust these outputs without independent verification. Code is available at \href{https://github.com/PKUDigitalHealth/ECG-R1}{here}. |
| title | ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.04279 |